Answer user questions strictly from OpenSpec documents.
npx skills add https://github.com/seanmars/ai-coding-setup --skill spectra-ask-seanmars
Please help me install this Agent Skill. Skill: spectra-ask Source: https://github.com/seanmars/ai-coding-setup/tree/main/spectra/skills/spectra-ask Command: npx skills add https://github.com/seanmars/ai-coding-setup --skill spectra-ask-seanmars
Answers to questions are always grounded in OpenSpec documents; if the documents do not contain the answer, it will say so instead of guessing.
Ask a question using the /spectra-ask prefix and let it search OpenSpec docs to provide a grounded answer.
High-intent search queries and answers about installing and using this skill.
Document-grounded Q&A from OpenSpec docs parses your query, searches the OpenSpec knowledge base, and delivers answers backed strictly by matched document content. It avoids general knowledge by enforcing a no-answer policy when relevant content is unavailable.
When OpenSpec documents lack the requested information, the system enforces a strict no-answer policy and states the content is unavailable instead of guessing or using general knowledge. This ensures all responses remain fully grounded in the OpenSpec corpus.
Yes, you can retrieve spec details, features, and change histories directly from the OpenSpec corpus. Query-driven discovery searches matched documents to inform answers, making it ideal for obtaining specific specification information.
No, the OpenSpec Q&A search does not use general knowledge to fill in missing document gaps. It operates strictly by parsing queries, searching the OpenSpec corpus for relevant material, and enforcing a no-answer policy when required content is unavailable.
To start asking questions, use the /spectra-ask prefix before your query. The system will search OpenSpec docs to provide a grounded answer derived strictly from the matched document sources.
patrykkopycinskiSet up a RAG pipeline with Elasticsearch for vector retrieval.
patronus-aiBuild RAG systems using vector databases and semantic search.
duozokkerIngest PDFs and documents into Agent2's knowledge base for search.
EngineerWithAIIntegrate vector databases and embedding models to build RAG systems for LLM applications.
